Class

MPSMatrixBatchNormalization

A batch normalization kernel that operates on matrices.

Declaration

class MPSMatrixBatchNormalization : MPSMatrixUnaryKernel

Topics

Initializers

init?(coder: NSCoder, device: MTLDevice)
init(device: MTLDevice)

Instance Properties

var computeStatistics: Bool
var epsilon: Float
var sourceInputFeatureChannels: Int
var sourceNumberOfFeatureVectors: Int

Instance Methods

func copy(with: NSZone?, device: MTLDevice?) -> Self
func encode(commandBuffer: MTLCommandBuffer, inputMatrix: MPSMatrix, meanVector: MPSVector, varianceVector: MPSVector, gammaVector: MPSVector?, betaVector: MPSVector?, resultMatrix: MPSMatrix)
func neuronParameterA() -> Float
func neuronParameterB() -> Float
func neuronParameterC() -> Float
func neuronType() -> MPSCNNNeuronType
func setNeuronType(MPSCNNNeuronType, parameterA: Float, parameterB: Float, parameterC: Float)

Relationships

Inherits From

Conforms To

See Also

Matrix Normalization Operations

class MPSMatrixBatchNormalizationGradient

A batch normalization gradient kernel that operates on matrices.